This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
AF
Login
John Hughes
Former MATS scholar working on scalable oversight and adversarial robustness.
Posts
Sorted by New
31
Best-of-N Jailbreaking
9d
1
46
Debating with More Persuasive LLMs Leads to More Truthful Answers
11mo
7
Wiki Contributions
Comments
Sorted by
Newest